Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to cannons or artillery

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of cannons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.88
    ©¶æ
    -0.85
    çīĪ
    -0.80
    Else
    -0.75
    æĸ¹
    -0.73
    mone
    -0.70
     ISI
    -0.68
     Genetics
    -0.68
    DragonMagazine
    -0.68
     Strawberry
    -0.67
    POSITIVE LOGITS
    balls
    1.34
    ball
    1.18
    lance
    1.12
     fodder
    1.02
     cannon
    1.01
     cannons
    0.95
     salute
    0.90
    nels
    0.87
     bombard
    0.87
    ptions
    0.86
    Act Density 0.017%

    No Known Activations